We present a novel framework for learning a joint shape and appearance model from a large set of un-labelled training examples in arbitrary positions and orientations. The shape and intensity spaces are unified by implicitly representing shapes as “images” in the space of distance transforms. A stochastic chord-based matching algorithm is developed to align photo-realistic training examples und...

The multi-object segmentation of images is one of the great challenges in computer vision. It contemplates the existence of many objects of possibly different classes in the same image. The introduction of shape descriptors into segmentation significantly improves its quality. However, it is difficult to optimize energies that involve shape priors because of their non-local nature. In the last ...

Key members: Péter Horváth [1] Zoltán Kató [2] Founded by: Hungarian Science and Technology Foundation (TET), Hungarian-French Cooperation (Balaton) [3] Hungarian Scientific Research Fund (OTKA) [4] European Union FP5 project IMAVIS PhD Scholarship of the Doctoral School in Mathematics and Computer Science of the University of Szeged [5] PhD Scholarship of the French Government Partners: Ariana...

Reconstructing 3D shapes from a sequence of images has long been a problem of interest in computer vision. Classical Structure from Motion (SfM) methods have attempted to solve this problem through projected point displacement & bundle adjustment. More recently, deep methods have attempted to solve this problem by directly learning a relationship between geometry and appearance. There is, howev...

Image segmentation with one shape prior is an important problem in computer vision. Most algorithms not only share a similar energy definition, but also follow a similar optimization strategy. Therefore, they all suffer from the same drawbacks in practice such as slow convergence and difficult-to-tune parameters. In this paper, by reformulating the energy cost function, we establish an importan...

To solve the ill-posed problem of shape-from-shading, the visual system often relies on prior assumptions such as illumination from above or viewpoint from above. Here we demonstrate that a third prior assumption is used--namely that the surface is globally convex. We use complex surface shapes that are realistically rendered with computer graphics, and we find that performance in a local-shape...

Cochlear implants can restore hearing to deaf or partially deaf patients. In order to plan the intervention, a model from high resolution μCT images is to be built from accurate cochlea segmentations and then, adapted to a patient-specific model. Thus, a precise segmentation is required to build such a model. We propose a new framework for segmentation of μCT cochlear images using random walks ...

We propose a new class of energies for segmentation of multiple foreground objects with a common shape prior. Our energy involves infinity constraints. For such energies standard expansion algorithm has no optimality guarantees and in practice gets stuck in bad local minima. Therefore, we develop a new move making algorithm, we call double expansion. In contrast to expansion, the new move allow...

The recently proposed sparse shape composition (SSC) opens a new avenue for shape prior modeling. Instead of assuming any parametric model of shape statistics, SSC incorporates shape priors on-the-fly by approximating a shape instance (usually derived from appearance cues) by a sparse combination of shapes in a training repository. Theoretically, one can increase the modeling capability of SSC ...

Key members: Péter Horváth [1] Zoltán Kató [2] Founded by: Hungarian Science and Technology Foundation (TET), Hungarian-French Cooperation (Balaton) [3] Hungarian Scientific Research Fund (OTKA) [4] European Union FP5 project IMAVIS PhD Scholarship of the Doctoral School in Mathematics and Computer Science of the University of Szeged [5] PhD Scholarship of the French Government Partners: Ariana...